Legal claims defining the scope of protection, as filed with the USPTO.
1. A method, comprising: recording an event in an event space by a plurality of cameras, the plurality of cameras recording a plurality of imaging frames; creating an imaging mask for each camera of the plurality of cameras; comparing, for each camera, the corresponding imaging mask to a corresponding sub-volume mask, the sub-volume mask generated by projecting from each camera each of a plurality of sub-volumes of the event space, and extracting at least one feature from at least one imaging mask, the at least one feature related to the event; saving the at least one feature to a subspace division mask; cropping the at least one feature from the imaging frames using the subspace division mask; and processing the at least one feature for a 3D reconstruction.
2. The method of claim 1 , further comprising: storing each of the sub-volume masks in a storage location.
3. The method of claim 1 , further comprising: storing each sub-volume mask associated with its respective camera in a storage location associated with that respective camera.
4. The method of claim 1 , further comprising: storing for each camera a listing of all sub-volumes having at least one feature in a matrix.
5. The method of claim 4 , wherein processing the at least one feature for a 3D reconstruction, further comprises: processing only the at least one feature in a sub-volume listed in the matrix.
6. The method of claim 1 , further comprising: determining a volume of the event space, wherein the plurality of sub-volumes are generated by dividing the volume into the plurality of sub-volumes.
7. The method of claim 1 , further comprising: performing stabilization to remove outlier features from the at least one feature.
8. A non-transitory computer readable storage medium including instructions stored thereon which, when executed by one or more processors, cause the one or more processors to: record an event in an event space by a plurality of cameras, the plurality of cameras recording a plurality of imaging frames; create an imaging mask for each camera of the plurality of cameras; compare, for each camera, the corresponding imaging mask to a corresponding sub-volume mask, the sub-volume mask generated by projecting from each camera each of a plurality of sub-volumes of the event space, and extracting at least one feature from at least one imaging mask, the at least one feature related to the event; save the at least one feature to a subspace division mask; crop the at least one feature from the imaging frames using the subspace division mask; and process the at least one feature for a 3D reconstruction.
9. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, further cause the one or more processors to: store each of the sub-volume masks in a storage location.
10. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, further cause the one or more processors to: store each sub-volume mask associated with its respective camera in a storage location associated with that respective camera.
11. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, further cause the one or more processors to: store for each camera a listing of all sub-volumes having at least one feature in a matrix.
12. The non-transitory computer readable storage medium of claim 11 , wherein the instructions to process the at least one feature for a 3D reconstruction, when executed, further cause the one or more processors to: process only the at least one feature in a sub-volume listed in the matrix.
13. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, further cause the one or more processors to: determine a volume of the event space, wherein the plurality of sub-volumes are generated by dividing the volume into the plurality of sub-volumes.
14. The non-transitory computer readable storage medium of claim 8 , wherein the instructions, when executed, further cause the one or more processors to: perform stabilization to remove outlier features from the at least one feature.
15. A system, comprising: a plurality of cameras for recording an event in a plurality of imaging frames; a controller coupled to the plurality of camera, the controller including instructions which, when executed by one or more processors, cause the controller to: create an imaging mask for each camera of the plurality of cameras; compare, for each camera, the corresponding imaging mask to a corresponding sub-volume mask, the sub-volume mask generated by projecting from each camera each of a plurality of sub-volumes of the event space, and extracting at least one feature from at least one imaging mask, the at least one feature related to the event; save the at least one feature to a subspace division mask; crop the at least one feature from the imaging frames using the subspace division mask; and process the at least one feature for a 3D reconstruction.
16. The system of claim 15 , wherein the instructions, when executed, further cause the controller to: store each of the sub-volume masks in a storage location.
17. The system of claim 15 , wherein the instructions, when executed, further cause the controller to: store each sub-volume mask associated with its respective camera in a storage location associated with that respective camera.
18. The system of claim 15 , wherein the instructions, when executed, further cause the controller to: store for each camera a listing of all sub-volumes having at least one feature in a matrix.
19. The system of claim 18 , wherein the instructions to process the at least one feature for a 3D reconstruction, when executed, further cause the controller to: process only the at least one feature in a sub-volume listed in the matrix.
20. The system of claim 15 , wherein the instructions, when executed, further cause the controller to: determine a volume of the event space, wherein the plurality of sub-volumes are generated by dividing the volume into the plurality of sub-volumes.
Unknown
November 26, 2019
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.